Scholarlink

Purpose <p>We evaluated a&#xa0;dedicated dose-reduced UHR-CT for head and neck imaging, combined with a&#xa0;novel deep learning reconstruction algorithm to assess its impact on image quality and radiation exposure.</p> Methods <p>Retrospective analysis of ninety-eight consecutive patients examined using a&#xa0;new body weight-adapted protocol. Images were reconstructed using adaptive iterative dose reduction and advanced intelligent Clear-IQ engine with an already established (DL-1) and a&#xa0;newly implemented reconstruction algorithm (DL-2). Additional thirty patients were scanned without body-weight-adapted dose reduction (DL-1-SD). Three readers evaluated subjective image quality regarding image quality and assessment of several anatomic regions. For objective image quality, signal-to-noise ratio and contrast-to-noise ratio were calculated for temporalis and masseteric muscle and the floor of the mouth. Radiation dose was evaluated by comparing the computed tomography dose index (CTDIvol) values.</p> Results <p>Deep learning-based reconstruction algorithms significantly improved subjective image quality (diagnostic acceptability: DL‑1 vs AIDR OR of 25.16 [6.30;38.85], <i>p</i> &lt; 0.001 and DL‑2 vs AIDR 720.15 [410.14;&gt; 999.99], <i>p</i> &lt; 0.001). Although higher doses (DL-1-SD) resulted in significantly enhanced image quality, DL‑2 demonstrated significant superiority over all other techniques across all defined parameters (<i>p</i> &lt; 0.001). Similar results were demonstrated for objective image quality, e.g. image noise (DL‑1 vs AIDR OR of 19.0 [11.56;31.24], <i>p</i> &lt; 0.001 and DL‑2 vs AIDR &gt; 999.9 [825.81;&gt; 999.99], <i>p</i> &lt; 0.001). Using weight-adapted kV reduction, very low radiation doses could be achieved (CTDIvol: 7.4 ± 4.2 mGy).</p> Conclusion <p>AI-based reconstruction algorithms in ultra-high resolution head and neck imaging provide excellent image quality while achieving very low radiation exposure.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Radiation Dose Reduction and Image Quality Improvement of UHR CT of the Neck by Novel Deep-learning Image Reconstruction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月30日

查看全文
  • Dominique Alya Messerle,
  • Nils F. Grauhan,
  • Laura Leukert,
  • Ann-Kathrin Dapper,
  • Roman H. Paul,
  • Andrea Kronfeld,
  • Bilal Al-Nawas,
  • Maximilian Krüger,
  • Marc A. Brockmann,
  • Ahmed E. Othman,
  • Sebastian Altmann

摘要

Purpose

We evaluated a dedicated dose-reduced UHR-CT for head and neck imaging, combined with a novel deep learning reconstruction algorithm to assess its impact on image quality and radiation exposure.

Methods

Retrospective analysis of ninety-eight consecutive patients examined using a new body weight-adapted protocol. Images were reconstructed using adaptive iterative dose reduction and advanced intelligent Clear-IQ engine with an already established (DL-1) and a newly implemented reconstruction algorithm (DL-2). Additional thirty patients were scanned without body-weight-adapted dose reduction (DL-1-SD). Three readers evaluated subjective image quality regarding image quality and assessment of several anatomic regions. For objective image quality, signal-to-noise ratio and contrast-to-noise ratio were calculated for temporalis and masseteric muscle and the floor of the mouth. Radiation dose was evaluated by comparing the computed tomography dose index (CTDIvol) values.

Results

Deep learning-based reconstruction algorithms significantly improved subjective image quality (diagnostic acceptability: DL‑1 vs AIDR OR of 25.16 [6.30;38.85], p < 0.001 and DL‑2 vs AIDR 720.15 [410.14;> 999.99], p < 0.001). Although higher doses (DL-1-SD) resulted in significantly enhanced image quality, DL‑2 demonstrated significant superiority over all other techniques across all defined parameters (p < 0.001). Similar results were demonstrated for objective image quality, e.g. image noise (DL‑1 vs AIDR OR of 19.0 [11.56;31.24], p < 0.001 and DL‑2 vs AIDR > 999.9 [825.81;> 999.99], p < 0.001). Using weight-adapted kV reduction, very low radiation doses could be achieved (CTDIvol: 7.4 ± 4.2 mGy).

Conclusion

AI-based reconstruction algorithms in ultra-high resolution head and neck imaging provide excellent image quality while achieving very low radiation exposure.